© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42190
    Prev
    Next
    INDEX
    Explanations

    given that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ional
    -0.08
    ønn
    -0.07
     Blasio
    -0.07
    ÏĦÏį
    -0.07
    åIJĮ声
    -0.07
    een
    -0.07
     Beispiel
    -0.07
    صÙĬب
    -0.07
    åIJĮæŶå°Ĩ
    -0.07
    æľĢä¼Łå¤§çļĦ
    -0.07
    POSITIVE LOGITS
    åħ¶
    0.11
    ç§įç§įåİŁåĽł
    0.11
     its
    0.09
    åħ¶åľ¨
    0.08
    åħ¶å¯¹
    0.08
     اÛĮÙĨÚ©Ùĩ
    0.08
    èĢĥèĻijåĪ°
    0.08
    åħ¶ä¸İ
    0.08
     име
    0.08
    åħ¶æīĢ
    0.07
    Activations Density 0.120%

    No Known Activations